Walk extraction strategies for node embeddings with RDF2Vec in knowledge graphs


Steenwinckel, Bram ; Vandewiele, Gilles ; Bonte, Pieter ; Weyns, Michael ; Paulheim, Heiko ; Ristoski, Petar ; De Turck, Filip ; Ongenae, Femke



DOI: https://doi.org/10.1007/978-3-030-87101-7_8
URL: https://link.springer.com/chapter/10.1007/978-3-03...
Additional URL: https://www.researchgate.net/publication/344180421...
Document Type: Conference or workshop publication
Year of publication: 2021
Book title: Database and expert systems applications - DEXA 2021 Workshops : BIOKDD, IWCFS, MLKgraphs, AI-CARES, ProTime, AISys 2021, virtual event, September 27–30, 2021, proceedings
The title of a journal, publication series: Communications in Computer and Information Science
Volume: 1479
Page range: 70-80
Conference title: DEXA 2021
Location of the conference venue: Online
Date of the conference: 27.-30.09.2021
Publisher: Kotsis, Gabriele ; Tjoa, A. Min ; Khalil, Ismail ; Moser, Bernhard ; Mashkoor, Atif ; Sametinger, Johannes ; Fensel, Anna ; Martinez-Gil, Jorge ; Fischer, Lukas ; Czech, Gerald ; Sobieczky, Florian ; Khan, Sohail
Place of publication: Cham
Publishing house: Springer International Publishing
ISBN: 978-3-030-87100-0 , 978-3-030-87101-7
ISSN: 1865-0929 , 1865-0937
Publication language: English
Institution: School of Business Informatics and Mathematics > Data Science (Paulheim 2018-)
Subject: 004 Computer science, internet
Keywords (English): knowledge graphs , embeddings , representation learning
Abstract: As Knowledge Graphs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modeling techniques. The original work proposed the Weisfeiler-Lehman kernel to improve the quality of the representations. However, in this work, we show that the Weisfeiler-Lehman kernel does little to improve walk embeddings in the context of a single Knowledge Graph. As an alternative, we examined five alternative strategies to extract information complementary to basic random walks and compare them on several benchmark datasets to show that research within this field is still relevant for node classification tasks.




Dieser Eintrag ist Teil der Universitätsbibliographie.




Metadata export


Citation


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item